Journal of Intelligent & Fuzzy Systems - Volume 45, issue 6

Authors: Gao, Danna | Zhang, Yin | Qiu, Hongjun

Article Type: Research Article

Abstract: Due to the large number of frames and low video resolution, tennis match videos cannot accurately identify and extract effective data, which reduces the level of fine analysis of tennis matches. In order to solve the problem of poor detection effect of small targets in tennis video, an automatic detection method of small targets in tennis video based on deep learning is proposed. Non-maximum suppression algorithm is used to determine the position of the target between different adjacent video image sequences, and SVM classifier is used to train a large number of target behaviors. According to the hierarchical structure of …dataset annotation, the hierarchical structure of tennis video for deep learning is optimized. The reconstruction algorithm is used to enhance the video image in the input VOC data set and improve the fine segmentation effect of the image. The difference video image is binarized to complete the automatic detection of small targets in tennis video. The experimental results show that the proposed method has high integrity of tennis video information collection, high recognition accuracy and short detection time. Show more

Keywords: Deep learning, tennis match, automatic target detection

DOI: 10.3233/JIFS-231167

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9199-9209, 2023

Authors: Chang, Jingjing | Zhao, Hui

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-231778

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9211-9221, 2023

Authors: Liu, Yang | Yi, Fulong | Ma, Yuhua | Wang, Yongfu

Article Type: Research Article

Abstract: To solve the problem that the existing semantic segmentation method is challenging to balance the two indicators of reasoning speed and accuracy under low-light conditions, a lightweight real-time semantic segmentation method that can run on embedded vehicle terminals under low-light conditions, namely, LCG-BiSeNetV2 is proposed. Firstly, the Zero-DCE++ method is introduced to preprocess the low-light video frames; Secondly, by improving the module of the BiSeNetV2 method and optimizing the downsampling convolution in the encoder structure, the semantic feature extraction ability of the BiSeNetV2 method has been significantly improved; Finally, the self-made road scene semantic segmentation dataset and the CAMVID dataset …were used for training and testing, the mIoU coefficient reaches 72.37% and 76.73%, and the reasoning speed reaches 148.91 Frames Per Second (FPS) and 136.75 FPS, which shows that the LCG-BiSeNetV2 method has achieved fast reasoning and precise semantic segmentation. Show more

Keywords: End-to-end, real-time, semantic segmentation, autonomous driving system, image enhancement

DOI: 10.3233/JIFS-230643

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9223-9237, 2023

Authors: Xie, Zhixin | Wang, Xiaofeng | Yang, Lan | Pang, Lichao | Zhao, Xingyu | Yang, Yi

Article Type: Research Article

Abstract: The survey propagation algorithm is the most effective information propagation algorithm for solving the 3-SAT problem. It can effectively solve the satisfiability problem when it converges. However, when the factor graph structure is complex, the algorithm often does not converge and the solution fails. In order to give a theoretical explanation to this phenomenon and to analyze the convergence of the survey propagation algorithm effectively, a connected treewidth model of the propositional formula was constructed by using the connected tree decomposition method, and the connected treewidth of the factor graph was calculated. The relationship between the connected treewidth and the …convergence of the survey propagation algorithm is established, and the convergence judgment condition of the survey propagation algorithm based on the connected tree width is given. Through experimental analysis, the results show that the method is effective, which is of great significance for analyzing the convergence analysis of other information propagation algorithms. Show more

Keywords: Survey propagation algorithm, convergence, connected treewidth, propositional formula, satisfiability problem

DOI: 10.3233/JIFS-223779

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9239-9252, 2023

Authors: Zhang, Ning | Jung, Kwansue

Article Type: Research Article

Abstract: High-quality development of socio-economic, ecological environment, tourism industry and natural resources in the Yellow River Basin is a major strategic task for national development. High-quality development in the Yellow River Basin still has a lot of room for improvement, so it is important for the coupled and coordinated development of water resources-socio-economic-ecological environment-tourism industry in the Yellow River Basin region. In this study, we focus on the major strategic issues of high quality development in the Yellow River Basin in the context of the above-mentioned background and the current forms and policies of sustainable development in China, and conduct research …on the theory and methods of assessing the sustainable development of regional water resources-socio-economic-ecological environment-tourism industry. However, by analyzing the existing research literature on sustainable development assessment, we find that most of them focus on a single area or two combinations of modal development studies, and focus on exploring micro-coupling mechanisms, so the generality of macro policy support is rather mediocre, which we fill this gap through this study. The study relies on an innovative macroscopic research perspective that draws pioneeringly on the quality function deployment (QFD) theory in the field of product quality management in marketing, which, it is worth stating, allows for a framework of research perspectives from a systematic and holistic perspective. In this framework, we will propose a G1-entropy value method for indicator importance (weight) assessment. It is worth stating that the G1 method used in this paper is different from the traditional G1 method in that we will introduce the identity information weights of experts to improve the reliability of the subjective assignment method. We will also construct an indicator system for studying the regional sustainable development issues in the Yellow River Basin on this basis, so as to complete the ranking and analysis of the nine provinces and the importance of indicators in the Yellow River Basin. This study will provide a comprehensive theoretical basis for Chinese government and related departments to formulate policies for the high-quality development of water resources, socio-economic, ecological environment and tourism industry in the Yellow River Basin, and also provide theoretical and empirical references for the analysis and assessment of similar international regional sustainability cases. Show more

Keywords: Analytical theory of sustainable development, quality function deployment, G1-entropy method, yellow river basin

DOI: 10.3233/JIFS-230920

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9253-9276, 2023

Authors: Nguyen, Phu Xuan-Vinh | Nguyen, Thu Hoang-Thien | Van Nguyen, Kiet | Nguyen, Ngan Luu-Thuy

Article Type: Research Article

Abstract: Multilingual pre-trained language models have achieved impressive results on most natural language processing tasks. However, the performance is inhibited due to capacity limitations and their under-representation of pre-training data, especially for languages with limited resources. This has led to the creation of tailored pre-trained language models, in which the models are pre-trained on large amounts of monolingual data or domain specific corpus. Nevertheless, compared to relying on multiple monolingual models, utilizing multilingual models offers the advantage of multilinguality, such as generalization on cross-lingual resources. To combine the advantages of both multilingual and monolingual models, we propose KDDA - a framework …that leverages monolingual models to a single multilingual model with the aim to improve sentence representation for Vietnamese. KDDA employs teacher-student framework and cross-lingual transfer that aims to adopt knowledge from two monolingual models (teachers) and transfers them into a unified multilingual model (student). Since the representations from the teachers and the student lie on disparate semantic spaces, we measure discrepancy between their distributions by using Sinkhorn Divergence - an optimal transport distance. We conduct experiments on two Vietnamese natural language understanding tasks, including machine reading comprehension and natural language inference. Experimental results show that our model outperforms other state-of-the-art models and yields competitive performances. Show more

Keywords: Natural language understanding, machine reading comprehension, natural language inference, knowledge distillation, optimal transport

DOI: 10.3233/JIFS-231485

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9277-9288, 2023

Authors: He, Xiaoquan | Dong, Fang

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-233020

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9289-9302, 2023

Authors: Ma, Qian | Jiang, Shuhao | Yang, Dandan | Cheng, Guangtao

Article Type: Research Article

Abstract: In recent years, the problem of influential spreader identification in complex networks has attracted extensive attention as its fundamental role in social network analysis, rumor controlling, viral marketing and other related fields. Centrality measures that consider different scales of neighborhood are commonly utilized for ranking node influence. The 2-hop neighborhood of the target node is deemed a suitable evaluation metric. However, as the network scale expands, only considering 2-hop neighborhood is overly restrictive. Furthermore, the interconnections among nodes are often disregarded. In this article, a new method named Limited Spreading Domain (LSD) is proposed to identify influential spreaders. LSD defines …the target node’s 2-hop neighborhood as basic domain and takes the neighbors who are 3–6 hops away from target node as extended domain. The influence of target node is modeled as diffusion along the paths with limited length in basic domain and extended domain. A series of experiments are conducted in eight real complex networks and results demonstrate that LSD outperforms common centralities in terms of accuracy, stability,distinguishability and scalability. Show more

Keywords: Complex network, influential spreaders, SIR model, centrality measure

DOI: 10.3233/JIFS-230258

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9303-9314, 2023

Authors: Xinyi, Zhang

Article Type: Research Article

Abstract: Visual art was originally measured by viewing and appreciating graphic works, and there was no previous research into ways to improve the quality of visual art. With the rapid development of visual arts and technology, the question of how to improve quality has become an urgent one. As the most cutting-edge and hottest concept in the international arena today, the development and application of metaverse technology has widely drawn the close attention of various industries, including management, economy, education, and art. However, there is no in-depth and clear research on the concept of metaverse in the field of art, especially …in the field of visual art. We believe that the creation of visual art in the context of metaverse will be an important direction for art development in the future, and can also greatly contribute to the improvement of the quality of metaverse visual art presentation. Therefore, we focus on the issue of visual art quality assessment in our research, and propose a theory and method of metaverse-oriented future visual art quality assessment. The method focuses on the G1-entropy value method to calculate the weights in visual arts, combines qualitative research with quantitative research, and proposes the improvement path and countermeasures for visual arts. In summary, our research aims to address the theoretical approaches to the design of the metaverse field architecture and the assessment of art quality for the future introduction of the metaverse. The main contributions of our research are focused on the following three aspects: 1. The construction of the visual art field architecture draws on the functional requirements analysis method of system science simulation, considering that the entire visual art metaverse field architecture is constructed at three levels: the bottom data support layer, the middle technical support layer and the upper technical application layer. 2. The G1-entropy combination weighting method is used to derive the importance ranking of visual art quality indicators and identify key factors, and to derive suggestions for quality improvement based on the key indicator factors. More importantly, we also build a field architecture for future-oriented visual arts in this study, which bridges the gap in the structural design of visual arts after the introduction of the future concept. Our present study makes a great contribution to the application of visual art quality enhancement, focusing on the analysis of new concepts and the improvement of old methods, building a new scene of organic combination of new technologies and traditional visual art, with practical research theoretical support for the promotion and progress of the disciplinary field. Show more

Keywords: Visual art, metaverse, field structure, G1 entropy method, index weights

DOI: 10.3233/JIFS-224571

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9315-9333, 2023

Authors: Liu, Shaohua | Xia, Caichu | Ye, Jun

Article Type: Research Article

Abstract: In large-section tunnel engineering, there is uncertain and inconsistent information in risk factors, due to complex geological, irregular hydrological conditions, limited survey technology, and inexperience of construction technicians. However, it is difficult for existing risk assessment methods to consider and express this uncertain information comprehensively, which will affect the accuracy of tunnel risk assessment. Hence, this paper develops a method of neutrosophic numbers similarity measure based on arcsine function to address the expression of uncertain information in the risk factors of large-section tunnel. The uncertain information in risk factors is considered comprehensively and the comprehensive weight of tunnel risk factors …is calculated by the analytic hierarchy process and the entropy weight method in this method, in order to provide a reference for similar tunnels. Show more

Keywords: Large-section tunnel, risk assessment, neutrosophic numbers, similarity measure, arcsine function

DOI: 10.3233/JIFS-231475

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 9335-9345, 2023